Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to definitions and qualifications in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spectrum
    -0.16
    .scalablytyped
    -0.15
    odied
    -0.14
    ckett
    -0.14
    å¬
    -0.14
     condu
    -0.14
    оÑĢалÑĮ
    -0.14
    amarin
    -0.14
     signature
    -0.13
    Ïįν
    -0.13
    POSITIVE LOGITS
     instrument
    0.17
     Chance
    0.17
     deton
    0.17
     factor
    0.17
     Instruments
    0.16
     weapon
    0.16
     matter
    0.15
    Challenge
    0.15
    æĻ´
    0.15
     weaponry
    0.15
    Act Density 0.027%

    No Known Activations